C# Class Encog.Neural.Flat.FlatNetwork

Afficher le fichier Open project: encog/encog-silverlight-core Class Usage Examples

Méthodes publiques

Méthode	Description
CalculateError ( IMLDataSet data ) : double	Calculate the error for this neural network. The error is calculated using root-mean-square(RMS).
ClearConnectionLimit ( ) : void	Clear any connection limits.
ClearContext ( ) : void	Clear any context neurons.
Clone ( ) : Object	Clone the network.
CloneFlatNetwork ( FlatNetwork result ) : void	Clone into the flat network passed in.
Compute ( double input, double output ) : void	Calculate the output for the given input.
DecodeNetwork ( double data ) : void	Decode the specified data into the weights of the neural network. This method performs the opposite of encodeNetwork.
EncodeNetwork ( ) : double[]	Encode the neural network to an array of doubles. This includes the network weights. To read this into a neural network, use the decodeNetwork method.
FlatNetwork ( ) : System	Default constructor.
FlatNetwork ( FlatLayer layers ) : System	Create a flat network from an array of layers.
FlatNetwork ( int input, int hidden1, int hidden2, int output, bool tanh ) : System	Construct a flat neural network.
HasSameActivationFunction ( ) : Type	Neural networks with only one type of activation function offer certain optimization options. This method determines if only a single activation function is used.
Init ( FlatLayer layers ) : void	Construct a flat network.
Randomize ( ) : void	Perform a simple randomization of the weights of the neural network between -1 and 1.
Randomize ( double hi, double lo ) : void	Perform a simple randomization of the weights of the neural network between the specified hi and lo.

Méthodes protégées

Méthode	Description
ComputeLayer ( int currentLayer ) : void	Calculate a layer.

Method Details

CalculateError() public méthode

Calculate the error for this neural network. The error is calculated using root-mean-square(RMS).

public CalculateError ( IMLDataSet data ) : double
data	IMLDataSet	The training set.
Résultat	double

ClearConnectionLimit() public méthode

Clear any connection limits.

public ClearConnectionLimit ( ) : void
Résultat	void

ClearContext() public méthode

Clear any context neurons.

public ClearContext ( ) : void
Résultat	void

Clone() public méthode

Clone the network.

public Clone ( ) : Object
Résultat	Object

CloneFlatNetwork() public méthode

Clone into the flat network passed in.

public CloneFlatNetwork ( FlatNetwork result ) : void
result	FlatNetwork	The network to copy into.
Résultat	void

Compute() public méthode

Calculate the output for the given input.

public Compute ( double input, double output ) : void
input	double	The input.
output	double	Output will be placed here.
Résultat	void

ComputeLayer() protected méthode

Calculate a layer.

protected ComputeLayer ( int currentLayer ) : void
currentLayer	int	The layer to calculate.
Résultat	void

DecodeNetwork() public méthode

Decode the specified data into the weights of the neural network. This method performs the opposite of encodeNetwork.

public DecodeNetwork ( double data ) : void
data	double	The data to be decoded.
Résultat	void

EncodeNetwork() public méthode

Encode the neural network to an array of doubles. This includes the network weights. To read this into a neural network, use the decodeNetwork method.

public EncodeNetwork ( ) : double[]
Résultat	double[]

FlatNetwork() public méthode

Default constructor.

public FlatNetwork ( ) : System
Résultat	System

FlatNetwork() public méthode

Create a flat network from an array of layers.

public FlatNetwork ( FlatLayer layers ) : System
layers	FlatLayer	The layers.
Résultat	System

FlatNetwork() public méthode

Construct a flat neural network.

public FlatNetwork ( int input, int hidden1, int hidden2, int output, bool tanh ) : System
input	int	Neurons in the input layer.
hidden1	int
hidden2	int
output	int	Neurons in the output layer.
tanh	bool	True if this is a tanh activation, false for sigmoid.
Résultat	System

HasSameActivationFunction() public méthode

Neural networks with only one type of activation function offer certain optimization options. This method determines if only a single activation function is used.

public HasSameActivationFunction ( ) : Type
Résultat	System.Type

Init() public méthode

Construct a flat network.

public Init ( FlatLayer layers ) : void
layers	FlatLayer	The layers of the network to create.
Résultat	void

Randomize() public méthode

Perform a simple randomization of the weights of the neural network between -1 and 1.

public Randomize ( ) : void
Résultat	void

Randomize() public méthode

Perform a simple randomization of the weights of the neural network between the specified hi and lo.

public Randomize ( double hi, double lo ) : void
hi	double	The network high.
lo	double	The network low.
Résultat	void